Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/manual-review.data-readiness)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/manual-review.data-readiness"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/manual-review.data-readiness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/manual-review.data-readiness"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/manual-review.data-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.10257 |
| Opus 5 | $0.00000 | $0.05129 |
| Sonnet 5 | $0.00000 | $0.02051 |
| Haiku 4.5 | $0.00000 | $0.01026 |
Grade A, and why
manual-review.data-readiness scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `[verify:api]` items（curl / ofetch 自帶 request body，主線跑完寫 annotation） How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime adapter boundary
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability it can prove; an absent or unverified capability remains blocked and MUST NOT be silently replaced by a neighbouring runtime.
Manual Review — Data Readiness & Actionability
Reference 檔。核心規約見
manual-review.md。本檔聚焦[review:ui]/[verify:ui]在 propose 階段就必須準備好驗收資料（sample identifier + 拆步驟 + seed），以及[review:ui]step actionability、@no-manual-review-checkbypass marker、截圖檔名 ↔ item id 配對。
Pre-Review Data Readiness（hard rule）
寫 ## 人工檢查 項目時，MUST 把驗收所需資料當成 item 的一部分在 propose 階段就準備好，不可叫使用者「找一張 X」「挑一筆 Y」。Review GUI 開頁的瞬間 = 使用者已能照 step 直接跑。
前置假設：本節規範的對象是「真正需要 user 親自跑」的 [review:ui] / [verify:ui] items。若 marker 本身誤標（例：把該由 agent 自驗的「按鈕應隱藏」標成 [review:ui]），先依 manual-review.evidence.md 的「[review:ui] 收斂原則」改 marker，再依本節準備資料。把該由 agent 做的事推給 user 是更嚴重的錯誤。
禁止的模糊指代
[review:ui] / [verify:ui] item 描述中 NEVER 出現下列模糊指代詞：
- 中：「某張」「某筆」「某個」「任一張」「任一筆」「隨便一張」「找一張」「挑一筆」「找某筆」「現有的一筆」「適合的一筆」
- En:
any X/some X/a record/pick one/find a X/an existing one（後接無具體 ID 時）
propose / ingest 階段命中即視為違反，MUST 改寫。
必填三件事
每條 [review:ui] / [verify:ui] item MUST 在 propose 階段同時做到：
- Sample inline 引用 — item 描述內直接寫具體 sample identifier（PK
WR-9001/ UUID / business keycard_uid=04A1B2C3/staff [email protected]等），讓 user 一眼看出該操作哪一筆 - 多步驟驗收條列 Step — 含 1+ 個分支、互斥狀態、對稱驗證、多角色切換時，MUST 拆
#N.Mscoped sub-items；每個 sub-item = 單一可執行 step（打開哪頁 → 點哪裡 → 應看到什麼） - Sample 持久化寫進 seed — 對應 sample MUST 由 propose 階段對應的
## N. Fixtures / Seed Plantask 寫進專案 seed 檔（supabase/seed.sql或 fallback path，見ux-completeness.md的「必填 Fixtures / Seed Plan」）。禁止只靠 dev DB 既有資料碰運氣、靠 ad-hoc INSERT 或 review 當下手動建 — 那些下次 reset DB 就消失，下個接手者重踩坑
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +8 lines 55fce33ec4b6
- 6d ago First seen · 415 lines · 0 tokens per session scan A 38bd09843e3e
manual-review.data-readiness is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,257 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
coverage-thresholds
Coverage threshold configuration patterns.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.